Approximation schemes for functional optimization problems
From MaRDI portal
Approximation schemes and suboptimal solutions for functional optimization problems with admissible solutions dependent on a large number of variables are investigated on the basis of the analysis for a sufficiently large number \(n\) of basis functions in the paper of \textit{V. Kurkova} and \textit{M. Sanguneti} [SIAM J. Optim. 15, 461--487 (2005; Zbl 1074.49008)] in which the critical term is of the form \(n^{- {1 \over 2}}\), multiplied by a certain norm of the optimal solution, called ``variation norm. In the present paper, the authors show that the upper bounds are of the same order \(n^{-\frac12}\) and the error of the approximate optimization can be obtained for various sets of admissible solutions defined in terms of variation norms with respect to different bases, if one suitably ``matches the approximation with the set of admissible solutions. Variation norms are compared for some variable-basis approximation schemes and are estimated in terms of spectral norms. The comparison is given for classical \(L_p\) and Sobolev's spaces with sets of admissible functions having finite variation norms with respect to some bases.
Recommendations
- Functional optimization by variable-basis approximation schemes
- Minimization of Error Functionals over Variable-Basis Functions
- A comparison between fixed-basis and variable-basis schemes for function approximation and functional optimization
- Estimates of variation with respect to a set and applications to optimization problems
- Rates of minimization of error functionals over Boolean variable-basis functions
- Error Estimates for Approximate Optimization by the Extended Ritz Method
- Best approximation by linear combinations of characteristic functions of half-spaces.
- Finite dimensional approximation to solutions of minimization problems in functional spaces
- scientific article; zbMATH DE number 5873303
- scientific article; zbMATH DE number 584512
Cites work
- A New Class of Incremental Gradient Methods for Least Squares Problems
- A recursive algorithm for nonlinear least-squares problems
- A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
- Approximating networks and extended Ritz method for the solution of functional optimization problems
- Bounds on rates of variable-basis and neural-network approximation
- Comparison of worst case errors in linear and neural network approximation
- Complexity of Gaussian-radial-basis networks approximating smooth functions
- Condition numbers and Ritz type methods in unconstrained optimization
- Error Estimates for Approximate Optimization by the Extended Ritz Method
- Functional optimal estimation problems and their solution by nonlinear approximation schemes
- Hinging hyperplanes for regression, classification, and function approximation
- scientific article; zbMATH DE number 447275 (Why is no real title available?)
- scientific article; zbMATH DE number 3425963 (Why is no real title available?)
- scientific article; zbMATH DE number 3888314 (Why is no real title available?)
- scientific article; zbMATH DE number 3126094 (Why is no real title available?)
- scientific article; zbMATH DE number 3953477 (Why is no real title available?)
- scientific article; zbMATH DE number 51537 (Why is no real title available?)
- scientific article; zbMATH DE number 124702 (Why is no real title available?)
- scientific article; zbMATH DE number 193014 (Why is no real title available?)
- scientific article; zbMATH DE number 3491650 (Why is no real title available?)
- scientific article; zbMATH DE number 778115 (Why is no real title available?)
- scientific article; zbMATH DE number 1405266 (Why is no real title available?)
- scientific article; zbMATH DE number 3206496 (Why is no real title available?)
- scientific article; zbMATH DE number 3314644 (Why is no real title available?)
- scientific article; zbMATH DE number 3329342 (Why is no real title available?)
- Minimization of Error Functionals over Variable-Basis Functions
- Optimization of approximating networks for optimal fault diagnosis
- Rates of minimization of error functionals over Boolean variable-basis functions
- The extended Ritz method for functional optimization: overview and applications to single-person and team optimal decision problems
- Universal approximation bounds for superpositions of a sigmoidal function
- Universal approximation by ridge computational models and neural networks: a survey
- Well-posed optimization problems
Cited in
(30)- Approximate maxima finding of continuous functions under restricted budget
- Approximation of the optimum function in procedures of parametric optimization
- Numerical reduced variable optimization methods via implicit functional dependence with applications
- Approximate dynamic programming for stochastic \(N\)-stage optimization with application to optimal consumption under uncertainty
- On the curse of dimensionality in the Ritz method
- Information complexity of functional optimization problems and their approximation schemes
- scientific article; zbMATH DE number 4139506 (Why is no real title available?)
- The extended Ritz method for functional optimization: overview and applications to single-person and team optimal decision problems
- scientific article; zbMATH DE number 3908183 (Why is no real title available?)
- scientific article; zbMATH DE number 13331 (Why is no real title available?)
- A comparison between fixed-basis and variable-basis schemes for function approximation and functional optimization
- Remarques sur un algorithme d'optimisation pour une classe de fonctionnelles sur ℝk
- An approximation method for the optimization of continuous functions ofnvariables by densifying their domains
- Can dictionary-based computational models outperform the best linear ones?
- Minimization of Error Functionals over Variable-Basis Functions
- scientific article; zbMATH DE number 2123490 (Why is no real title available?)
- Suboptimal Policies for Stochastic N-Stage Optimization: Accuracy Analysis and a Case Study from Optimal Consumption
- Geometric versus arithmetic difference and H^1-seminorm versus L^2-norm in function approximation
- Error Estimates for Approximate Optimization by the Extended Ritz Method
- Functional optimization by variable-basis approximation schemes
- Some comparisons of complexity in dictionary-based and linear computational models
- scientific article; zbMATH DE number 3063113 (Why is no real title available?)
- Computational discretization algorithms for functional inequality constrained optimization
- Approximating networks and extended Ritz method for the solution of functional optimization problems
- Suboptimal solutions to dynamic optimization problems via approximations of the policy functions
- Choice of approximation bases used in computational functional algorithms for approximating probability densities for a given sample
- Improved universal approximation with neural networks studied via affine-invariant subspaces of \(L_2 (\mathbb{R}^n)\)
- New insights into Witsenhausen's counterexample
- Management of water resource systems in the presence of uncertainties by nonlinear approximation techniques and deterministic sampling
- Estimates of variation with respect to a set and applications to optimization problems
This page was built for publication: Approximation schemes for functional optimization problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1024253)
